Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering safety and idempotency. The description adds value by disclosing the per-profile credit cost (0.1 credit) and the access limitation that some account tiers may receive a free 403, which is not present in the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three short sentences with no filler: the core purpose comes first, followed by cost and access caveats. It is efficient and easy to scan, though starting with an imperative verb like 'Get' would improve structure slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with annotations covering safety, the description covers cost and access, but it does not specify whether 'Accounts' means full profile objects or just IDs, which matters given sibling tools like get_follower_ids. Pagination is inferred from the cursor parameter in the schema, but with no output schema, an explicit statement of return format would make the tool more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75% with clear descriptions for user, fresh, and cursor, but count lacks a description. The description does not add direct parameter-level meaning; the '0.1 credit per profile' line hints at count's effect on cost but does not explain its semantics. With moderate schema coverage, the description could do more but does not contradict or significantly enhance the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Accounts a user follows' clearly identifies the tool's resource, and the pairing with sibling tools like get_followers and get_follower_ids makes the distinction easy to infer. It lacks an explicit verb such as 'get' or 'list', so it is not as direct as it could be, but the meaning is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is used to retrieve the accounts a user follows, which sets it apart from siblings, but it does not explicitly state when to choose this over alternatives like get_followers or get_follower_ids. No exclusion criteria or alternative recommendations are provided; the account-tier caveat is a behavioral warning, not usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.